plot.proximity {randomSurvivalForest} | R Documentation |
Multidimensional scaling plot of the proximity matrix.
plot.proximity(x, plot = TRUE, ...)
x |
An object of class |
plot |
Should proximity be plotted. |
... |
Further arguments passed to or from other methods. |
Extracts the proximity information from the object x
and
transforms this to a symmetric proximity matrix. Dissimilarities
between points are converted into distances using the multidimensional
scaling function cmdscale
and then plotted. Overlayed on the
plot are mortality values, rescaled from 1-100, with 1 indicating low
mortality, and 100 indicating high mortality. Mortality values will
be well separated in successful analyses. Note that points in blue
correspond to events, whereas black points are censored observations.
Invisibly, the proximity matrix with entries transformed to relative frequencies.
Hemant Ishwaran hemant.ishwaran@gmail.com
Udaya B. Kogalur kogalurshear@gmail.com
rsf
,
predict.rsf
.
data(pbc, package = "randomSurvivalForest") pbc.prox.out <- rsf(Surv(days,status) ~ ., pbc, ntree = 100, proximity = TRUE) plot.proximity(pbc.prox.out)